Skip to Main content Skip to Navigation
Conference papers

Fouille de données pour associer des noms de sessions aux articles scientifiques

Solen Quiniou 1 Peggy Cellier 2 Thierry Charnois 3
1 TALN
LINA - Laboratoire d'Informatique de Nantes Atlantique
2 LIS - Logical Information Systems
IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : In this paper, we present a proposition based on data mining to tackle the DEFT 2014 challenge. We focus on task 4 which consists of identifying the right conference session for scientific papers. The proposed approach is based on a combination of two data mining techniques. Sequence mining extracts frequent phrases in scientific papers in order to build paper and session descriptions. Then, those descriptions of papers and sessions are used to create a graph which represents shared descriptions. A graph mining technique is applied on the graph in order to extract a collection of homogenous sub-graphs corresponding to sets of papers associated to sessions.
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01113464
Contributor : Solen Quiniou <>
Submitted on : Thursday, February 5, 2015 - 3:12:33 PM
Last modification on : Tuesday, March 10, 2020 - 10:10:03 AM
Document(s) archivé(s) le : Wednesday, May 6, 2015 - 10:25:26 AM

File

deft2014_06_lina.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01113464, version 1

Citation

Solen Quiniou, Peggy Cellier, Thierry Charnois. Fouille de données pour associer des noms de sessions aux articles scientifiques. DEFT 2014, Jul 2014, Marseille, France. ⟨hal-01113464⟩

Share

Metrics

Record views

662

Files downloads

201